{"id":"https://openalex.org/W4414850539","doi":"https://doi.org/10.1109/iccv51701.2025.00987","title":"X-Dancer: Expressive Music to Human Dance Video Generation","display_name":"X-Dancer: Expressive Music to Human Dance Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414850539","doi":"https://doi.org/10.1109/iccv51701.2025.00987"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.17414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100313717","display_name":"Zeyuan Chen","orcid":"https://orcid.org/0009-0008-4504-7108"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyuan Chen","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034345096","display_name":"Hongyi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyi Xu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261844","display_name":"Guoxian Song","orcid":"https://orcid.org/0000-0002-3664-572X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoxian Song","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108738757","display_name":"You Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You Xie","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046566373","display_name":"Chenxu Zhang","orcid":"https://orcid.org/0000-0003-1645-9695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxu Zhang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045561112","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0001-5485-6398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084896808","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-2580-4710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078191425","display_name":"Ding Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Chang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107468462","display_name":"Linjie Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Luo","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10602","last_page":"10611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12051","display_name":"Diversity and Impact of Dance","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12051","display_name":"Diversity and Impact of Dance","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10758","display_name":"Cinema and Media Studies","score":0.9072999954223633,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dance","display_name":"Dance","score":0.761900007724762},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5644000172615051},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5443000197410583},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3578000068664551},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3276999890804291},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3237999975681305},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3154999911785126},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.761900007724762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199000120162964},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5076000094413757},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.3012000024318695},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.17414","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17414","pdf_url":"https://arxiv.org/pdf/2502.17414","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.17414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.17414","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.17414","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17414","pdf_url":"https://arxiv.org/pdf/2502.17414","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,142],"present":[1],"X-Dancer,":[2],"a":[3,20,29,55,85,110,145,171,187],"novel":[4],"zero-shot":[5],"music-driven":[6],"image":[7,178],"animation":[8],"pipeline":[9],"that":[10,38,69,149,195],"creates":[11],"diverse":[12,202],"and":[13,41,49,61,80,132,135,140,164,203,216,219],"long-range":[14],"lifelike":[15],"human":[16,72,117],"dance":[17,63,90,153,205],"videos":[18],"from":[19,115],"single":[21],"static":[22],"image.":[23],"As":[24],"its":[25],"core,":[26],"we":[27,107,169],"introduce":[28],"unified":[30],"transformer-diffusion":[31],"framework,":[32],"featuring":[33],"an":[34],"autoregressive":[35],"transformer":[36,147],"model":[37,57,148,220],"synthesize":[39],"extended":[40],"music-synchronized":[42],"token":[43,113,155],"sequences":[44],"for":[45,224],"2D":[46,89,116],"body,":[47],"head":[48,139],"hands":[50],"poses,":[51],"which":[52],"then":[53,143],"guide":[54],"diffusion":[56,172],"to":[58,160,174,199],"produce":[59,200],"coherent":[60],"realistic":[62],"video":[64],"frames.":[65],"Unlike":[66],"traditional":[67],"methods":[68,210],"primarily":[70],"generate":[71],"motion":[73,166],"in":[74,211],"3D,":[75],"X-Dancer":[76,196],"addresses":[77],"data":[78],"limitations":[79],"enhances":[81],"scalability":[82],"by":[83],"modeling":[84],"wide":[86],"spectrum":[87],"of":[88,213],"motions,":[91],"capturing":[92],"their":[93],"nuanced":[94],"alignment":[95],"with":[96,121,179],"musical":[97,162],"beats":[98],"through":[99,184],"readily":[100],"available":[101,223],"monocular":[102],"videos.":[103],"To":[104],"achieve":[105],"this,":[106],"first":[108],"build":[109],"spatially":[111],"compositional":[112],"representation":[114],"pose":[118,154,182],"labels":[119],"associated":[120],"keypoint":[122],"confidences,":[123],"encoding":[124],"both":[125,161,201],"large":[126],"articulated":[127],"body":[128],"movements":[129],"(e.g.,":[130,138],"upper":[131],"lower":[133],"body)":[134],"fine-grained":[136],"motions":[137],"hands).":[141],"design":[144],"music-to-motion":[146],"autoregressively":[150],"generates":[151],"music-aligned":[152],"sequences,":[156],"incorporating":[157],"global":[158],"attention":[159],"style":[163],"prior":[165],"context.":[167],"Finally":[168],"leverage":[170],"backbone":[173],"animate":[175],"the":[176],"reference":[177],"these":[180],"synthesized":[181],"tokens":[183],"AdaIN,":[185],"forming":[186],"fully":[188],"differentiable":[189],"end-to-end":[190],"framework.":[191],"Experimental":[192],"results":[193],"demonstrate":[194],"is":[197],"able":[198],"characterized":[204],"videos,":[206],"substantially":[207],"outperforming":[208],"state-of-the-art":[209],"term":[212],"diversity,":[214],"expressiveness":[215],"realism.":[217],"Code":[218],"will":[221],"be":[222],"research":[225],"purposes.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
